AUTHOR=Hu Shaoxiang , Liao Zhiwu , Hou Rong , Chen Peng 

TITLE=Characteristic Sequence Analysis of Giant Panda Voiceprint

JOURNAL=Frontiers in Physics

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2022.839699

DOI=10.3389/fphy.2022.839699

ISSN=2296-424X

ABSTRACT=By analyzing the voiceprint characteristics of giant panda's voice, this paper proposes a giant panda individual recognition method based on the characteristics of composite Mel composite frequency cepstrum coefficient(CMFCC), and proves that the characteristic sequence of CMFCC has long-range dependent characteristics. Firstly, MFCC (Mel composite frequency cepstrum coefficient) with low frequency resolution is obtained by Mel filter bank; Then, the inverse Mel frequency cepstrum coefficient IMFCC features of giant panda calls are extracted. The CMFCC characteristic sequence of giant panda Voice composed of MFCC and IMFCC improves the resolution of high and low frequency resolution characteristics of giant panda voice; Finally, the first-order difference characteristic parameters of MFCC are integrated to obtain the difference characteristics between frames. Through experiments, the improvement of system recognition effect is verified, and the recognition accuracy meets the theoretical expectation.